Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of alcoholic beverages and their availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lett
    -0.14
    aux
    -0.14
     relay
    -0.14
    zim
    -0.13
    .BLL
    -0.13
    èĶ
    -0.13
     Wrap
    -0.13
     fib
    -0.13
     Barnes
    -0.13
    amo
    -0.13
    POSITIVE LOGITS
     spirits
    0.42
     rum
    0.39
     cogn
    0.33
     Spirits
    0.32
     spirit
    0.30
     Rum
    0.30
     lique
    0.28
     brand
    0.28
     gin
    0.27
    spir
    0.26
    Act Density 0.190%

    No Known Activations